[merged mm-stable] memcg-replace-stats_flush_lock-with-an-atomic.patch removed from -mm tree

[Andrew Morton <akpm@linux-foundation.org>]

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain, Size: 5272 bytes --]


The quilt patch titled
     Subject: memcg: replace stats_flush_lock with an atomic
has been removed from the -mm tree.  Its filename was
     memcg-replace-stats_flush_lock-with-an-atomic.patch

This patch was dropped because it was merged into the mm-stable branch
of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

------------------------------------------------------
From: Yosry Ahmed <yosryahmed@google.com>
Subject: memcg: replace stats_flush_lock with an atomic
Date: Thu, 30 Mar 2023 19:17:57 +0000

As Johannes notes in [1], stats_flush_lock is currently used to:
(a) Protect updated to stats_flush_threshold.
(b) Protect updates to flush_next_time.
(c) Serializes calls to cgroup_rstat_flush() based on those ratelimits.

However:

1. stats_flush_threshold is already an atomic

2. flush_next_time is not atomic. The writer is locked, but the reader
   is lockless. If the reader races with a flush, you could see this:

                                        if (time_after(jiffies, flush_next_time))
        spin_trylock()
        flush_next_time = now + delay
        flush()
        spin_unlock()
                                        spin_trylock()
                                        flush_next_time = now + delay
                                        flush()
                                        spin_unlock()

   which means we already can get flushes at a higher frequency than
   FLUSH_TIME during races. But it isn't really a problem.

   The reader could also see garbled partial updates if the compiler
   decides to split the write, so it needs at least READ_ONCE and
   WRITE_ONCE protection.

3. Serializing cgroup_rstat_flush() calls against the ratelimit
   factors is currently broken because of the race in 2. But the race
   is actually harmless, all we might get is the occasional earlier
   flush. If there is no delta, the flush won't do much. And if there
   is, the flush is justified.

So the lock can be removed all together. However, the lock also served
the purpose of preventing a thundering herd problem for concurrent
flushers, see [2]. Use an atomic instead to serve the purpose of
unifying concurrent flushers.

[1]https://lore.kernel.org/lkml/20230323172732.GE739026@cmpxchg.org/
[2]https://lore.kernel.org/lkml/20210716212137.1391164-2-shakeelb@google.com/

Link: https://lkml.kernel.org/r/20230330191801.1967435-5-yosryahmed@google.com
Signed-off-by: Yosry Ahmed <yosryahmed@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Josef Bacik <josef@toxicpanda.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Michal Koutný <mkoutny@suse.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vasily Averin <vasily.averin@linux.dev>
Cc: Zefan Li <lizefan.x@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/memcontrol.c |   18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

--- a/mm/memcontrol.c~memcg-replace-stats_flush_lock-with-an-atomic
+++ a/mm/memcontrol.c
@@ -586,8 +586,8 @@ mem_cgroup_largest_soft_limit_node(struc
  */
 static void flush_memcg_stats_dwork(struct work_struct *w);
 static DECLARE_DEFERRABLE_WORK(stats_flush_dwork, flush_memcg_stats_dwork);
-static DEFINE_SPINLOCK(stats_flush_lock);
 static DEFINE_PER_CPU(unsigned int, stats_updates);
+static atomic_t stats_flush_ongoing = ATOMIC_INIT(0);
 static atomic_t stats_flush_threshold = ATOMIC_INIT(0);
 static u64 flush_next_time;
 
@@ -637,15 +637,19 @@ static inline void memcg_rstat_updated(s
 
 static void __mem_cgroup_flush_stats(void)
 {
-	unsigned long flag;
-
-	if (!spin_trylock_irqsave(&stats_flush_lock, flag))
+	/*
+	 * We always flush the entire tree, so concurrent flushers can just
+	 * skip. This avoids a thundering herd problem on the rstat global lock
+	 * from memcg flushers (e.g. reclaim, refault, etc).
+	 */
+	if (atomic_read(&stats_flush_ongoing) ||
+	    atomic_xchg(&stats_flush_ongoing, 1))
 		return;
 
-	flush_next_time = jiffies_64 + 2*FLUSH_TIME;
+	WRITE_ONCE(flush_next_time, jiffies_64 + 2*FLUSH_TIME);
 	cgroup_rstat_flush_atomic(root_mem_cgroup->css.cgroup);
 	atomic_set(&stats_flush_threshold, 0);
-	spin_unlock_irqrestore(&stats_flush_lock, flag);
+	atomic_set(&stats_flush_ongoing, 0);
 }
 
 void mem_cgroup_flush_stats(void)
@@ -656,7 +660,7 @@ void mem_cgroup_flush_stats(void)
 
 void mem_cgroup_flush_stats_ratelimited(void)
 {
-	if (time_after64(jiffies_64, flush_next_time))
+	if (time_after64(jiffies_64, READ_ONCE(flush_next_time)))
 		mem_cgroup_flush_stats();
 }
 
_

Patches currently in -mm which might be from yosryahmed@google.com are

memcg-sleep-during-flushing-stats-in-safe-contexts.patch
workingset-memcg-sleep-when-flushing-stats-in-workingset_refault.patch
vmscan-memcg-sleep-when-flushing-stats-during-reclaim.patch
memcg-do-not-modify-rstat-tree-for-zero-updates.patch
memcg-page_cgroup_ino-get-memcg-from-the-pages-folio.patch
mm-vmscan-ignore-non-lru-based-reclaim-in-memcg-reclaim.patch
mm-vmscan-move-set_task_reclaim_state-near-flush_reclaim_state.patch
mm-vmscan-refactor-updating-current-reclaim_state.patch